LLM Guard

LLM Guard is an open-source security toolkit for LLM applications, from Protect AI. It wraps model calls with input scanners (prompt injection, toxicity, secrets, code, banned topics) and output scanners (toxicity, bias, sensitive data, relevance, factual consistency).

It sanitizes prompts, detects harmful language and prevents data leakage. It installs via pip. Protect AI was acquired by Palo Alto Networks. MIT licensed.

The GitHub repository was archived in July 2026 and no longer receives updates. The code stays available under its licence; new projects should weigh that against maintained alternatives.